polygon-io/mcp_polygon

> :test_tube: This project is experimental and could be subject to breaking changes.
Massive.com MCP Server
A Model Context Protocol (MCP) server that provides access to the full Massive.com financial data API through an LLM-friendly interface.
Rather than exposing one tool per endpoint, this server gives the LLM three composable tools — **search**, **call**, and **query** — that cover the entire Massive.com API surface. Data can be stored in an in-memory SQLite database, and enriched with built-in financial functions.
> [!TIP]
> Don't want to install anything? Massive hosts this server at https://mcp.massive.com.
> See the AI Tools quickstart for setup in each client.
Tools
| Tool | Description |
|---|---|
| search_endpoints | Search for API endpoints and built-in functions by natural language query. Returns titles, path patterns, and descriptions. Set detail to "more" for query parameter docs, or "verbose" for full documentation. Use max_results to limit results. |
| call_api | Call any Massive.com REST API endpoint. Supports storing results as an in-memory database table (store_as) and applying post-processing functions (apply). Paginated responses include a next-page hint. |
| query_data | Run SQL against stored SQLite DB. Supports SHOW TABLES, DESCRIBE , DROP TABLE , CTEs, window functions, and more. Results can also be post-processed with apply. |
Built-in Functions
Functions can be applied to API results or query output via the apply parameter on call_api and query_data. Use search_endpoints with scope="functions" to discover them.
| Category | Functions |
|---|---|
| **Greeks** | bs_price, bs_delta, bs_gamma, bs_theta, bs_vega, bs_rho — Black-Scholes option pricing and greeks |
| **Returns** | simple_return, log_return, cumulative_return, sharpe_ratio, sortino_ratio |
| **Technical** | sma (simple moving average), ema (exponential moving average) |
Data Coverage
The server dynamically indexes all Massive.com API endpoints at startup from llms.txt, so it automatically stays in sync with the API. Coverage includes:
- Stock, options, forex, crypto, and futures aggregates
- Real-time and historical trades and quotes
- Market snapshots, gainers/losers
- Ticker details and reference data
- Dividends, splits, IPOs
- Financial fundamentals
- Analyst ratings and news (Benzinga)
- Treasury yields, inflation data
- Market status and holidays
Installation
Prerequisites
- Python 3.12+
- A Massive.com API key [![Button]][Link]
- Astral UV (v0.4.0+)
Claude Code
First, install Claude Code
Install the MCP server, then register it with Claude Code:
To upgrade to a new version later:
> [!NOTE]
> **Upgrading from uvx or uv run --with?** Previous versions recommended uvx --from ... mcp_massive or uv run --with. These commands download dependencies on every cold start, which can cause the server to exceed Claude's 30-second connection timeout. Switch to uv tool install as shown above — it downloads dependencies once and starts instantly after that.
This command will install the MCP server in your current project.
If you want to install it globally, you can run the command with -s flag.
See claude mcp add --help for more options.
To start Claude Code, run claude in your terminal.
- If this is your first time using, follow the setup prompts to authenticate